cgroup: remove synchronize_rcu() from cgroup_diput()
Free cgroup via call_rcu(). The actual work is done through
workqueue.
Signed-off-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 8118a31..900af59 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -203,6 +203,7 @@
/* For RCU-protected deletion */
struct rcu_head rcu_head;
+ struct work_struct free_work;
/* List of events which userspace want to receive */
struct list_head event_list;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index af99391..02e4f20 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -852,12 +852,52 @@
return inode;
}
+static void cgroup_free_fn(struct work_struct *work)
+{
+ struct cgroup *cgrp = container_of(work, struct cgroup, free_work);
+ struct cgroup_subsys *ss;
+
+ mutex_lock(&cgroup_mutex);
+ /*
+ * Release the subsystem state objects.
+ */
+ for_each_subsys(cgrp->root, ss)
+ ss->css_free(cgrp);
+
+ cgrp->root->number_of_cgroups--;
+ mutex_unlock(&cgroup_mutex);
+
+ /*
+ * Drop the active superblock reference that we took when we
+ * created the cgroup
+ */
+ deactivate_super(cgrp->root->sb);
+
+ /*
+ * if we're getting rid of the cgroup, refcount should ensure
+ * that there are no pidlists left.
+ */
+ BUG_ON(!list_empty(&cgrp->pidlists));
+
+ simple_xattrs_free(&cgrp->xattrs);
+
+ ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id);
+ kfree(cgrp);
+}
+
+static void cgroup_free_rcu(struct rcu_head *head)
+{
+ struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head);
+
+ schedule_work(&cgrp->free_work);
+}
+
static void cgroup_diput(struct dentry *dentry, struct inode *inode)
{
/* is dentry a directory ? if so, kfree() associated cgroup */
if (S_ISDIR(inode->i_mode)) {
struct cgroup *cgrp = dentry->d_fsdata;
- struct cgroup_subsys *ss;
+
BUG_ON(!(cgroup_is_removed(cgrp)));
/* It's possible for external users to be holding css
* reference counts on a cgroup; css_put() needs to
@@ -865,34 +905,7 @@
* the reference count in order to know if it needs to
* queue the cgroup to be handled by the release
* agent */
- synchronize_rcu();
-
- mutex_lock(&cgroup_mutex);
- /*
- * Release the subsystem state objects.
- */
- for_each_subsys(cgrp->root, ss)
- ss->css_free(cgrp);
-
- cgrp->root->number_of_cgroups--;
- mutex_unlock(&cgroup_mutex);
-
- /*
- * Drop the active superblock reference that we took when we
- * created the cgroup
- */
- deactivate_super(cgrp->root->sb);
-
- /*
- * if we're getting rid of the cgroup, refcount should ensure
- * that there are no pidlists left.
- */
- BUG_ON(!list_empty(&cgrp->pidlists));
-
- simple_xattrs_free(&cgrp->xattrs);
-
- ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id);
- kfree(cgrp);
+ call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
} else {
struct cfent *cfe = __d_cfe(dentry);
struct cgroup *cgrp = dentry->d_parent->d_fsdata;
@@ -1391,6 +1404,7 @@
INIT_LIST_HEAD(&cgrp->allcg_node);
INIT_LIST_HEAD(&cgrp->release_list);
INIT_LIST_HEAD(&cgrp->pidlists);
+ INIT_WORK(&cgrp->free_work, cgroup_free_fn);
mutex_init(&cgrp->pidlist_mutex);
INIT_LIST_HEAD(&cgrp->event_list);
spin_lock_init(&cgrp->event_list_lock);